Research And Implementation Of Early Warning System For Infectious Diseases Based On Machine Learning

Infectious diseases are the second leading cause of human death worldwide.They have caused considerable impacts and long-term threats to human health,social stability and economic development,and have aroused great concern in various fields.Since the 21st century,computer technology has developed rapidly,and machine learning gradually into the public attention.It is integrated into the field of health care and has played a huge role in the prediction of infectious diseases.At present,the work of integrating machine learning algorithms into the prediction of infectious diseases needs a system platform as a support.An infectious disease monitoring system based on machine learning provides an important reference for a specific infectious disease.The system facilitates the implementation of control policies.It can advance the process of public health safety and prevention of infectious diseases from a technical level.This thesis designs and implements an early warning system for infectious diseases based on machine learning.The Web side of the system is built by the framework of Django.In addition,a WeChat applet has been developed to make it easy for users to understand the latest predictions at all times and places.The main functions of the system include monitoring of climate data and pollution index,prediction of infectious diseases,the notification of warning,data visualization,management of latest research information and user management.The key technologies used in this thesis include the combination of principal component analysis and gated recurrent unit(PCA+GRU),crawler,Echarts visualization,etc.PCA+GRU is mainly used in the design of infectious disease prediction module to predict the number of tuberculosis patients in Huai’an City.In addition,PCA+GRU,KNN,LSTM,CNN,GRU and PCA+CNN were trained and tested on the same set of data.The results indicated that PCA+GRU has certain advantages in the prediction of infectious diseases with tuberculosis as an example.